CN109526027A - A kind of cell capacity optimization method, device, equipment and computer storage medium - Google Patents
A kind of cell capacity optimization method, device, equipment and computer storage medium Download PDFInfo
- Publication number
- CN109526027A CN109526027A CN201811424903.7A CN201811424903A CN109526027A CN 109526027 A CN109526027 A CN 109526027A CN 201811424903 A CN201811424903 A CN 201811424903A CN 109526027 A CN109526027 A CN 109526027A
- Authority
- CN
- China
- Prior art keywords
- cell
- data
- network public
- target cell
- critical data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/0289—Congestion control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/06—Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/04—Wireless resource allocation
- H04W72/044—Wireless resource allocation based on the type of the allocated resource
- H04W72/0453—Resources in frequency domain, e.g. a carrier in FDMA
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a kind of cell capacity optimization method, device, equipment and computer storage mediums.Wherein, cell capacity optimization method includes: to obtain multiple groups critical data relevant to the cell load of multiple cells in region to be optimized in a plurality of network public-opinion data；Predict that cell load will be in the Target cell of congestion state in multiple cells according to multiple groups critical data and a plurality of network public-opinion data；The cell categories according to belonging to Target cell carry out capacity optimization to Target cell.According to embodiments of the present invention, it can predict that cell load will be in the Target cell of congestion state according to network public-opinion data, to carry out capacity optimization to Target cell in time.
Description
Technical field
The invention belongs to mobile communication technology field more particularly to a kind of cell capacity optimization method, device, equipment and
Computer storage medium.
Background technique
Currently, the method that the existing capacity for cell optimizes is to pass through operation and maintenance center (Operation
And Maintenance Center, OMC) periodically acquire capacity class index, and by collected capacity class index with
Weekly granularity convergence carries out manual examination and verification according to the capacity class index of each cell of carrier frequency dilatation standard, when capacity class index reaches
When dilatation thresholding, increase the hardware device of cell, to carry out dilatation to cell in a manner of increasing carrier frequency.
Under normal circumstances, carrier frequency dilatation standard can be determined, thus root according to the cell classification of great Bao, middle packet, parcel
According to the carrier frequency dilatation standard, judges that each cell seven under different classifications is per day and whether reach from the capacity class index of busy
Dilatation thresholding, when arbitrary cells seven are per day reaches dilatation thresholding from the capacity class index of busy, it is increased carrier frequency with into
Row dilatation.The carrier frequency dilatation standard of cell under different classifications can be as shown in table 1.
1 carrier frequency dilatation standard scale of table
Wherein, cell can be cell utilization rate maximum one hour in 24 hours one day from busy, and cell utilization rate is
Maximum value in upstream utilization or downstream utilization.
According to table 1, when arbitrary cells meet: " effective RRC number of users reaches dilatation thresholding " and " upstream utilization
Or downstream utilization reaches dilatation thresholding " and when " uplink traffic or downlink traffic reach dilatation thresholding ", determine need it is small to this
Area carries out dilatation.
Although can be realized to a certain extent using the above method and carry out asking for capacity optimization to the cell of load too high
Topic, still, since current data acquisition interface is more traditional single, the capacity class index of OMC acquisition be unique dilatation according to
According to, cause reference frame dimension more single so that the capacity problem of cell judgement inaccuracy.In addition, by manually monitoring
And the load condition of cell is analyzed, it then determines whether to carry out dilatation to the cell, can not find that the capacity of cell is set in time
The reasonability set results in a finding that the hysteresis quality of the capacity problem of cell, the capacity requirement of cell can not be also prejudged, for cell
Capacity problem occur trend can not pointedly analyze.Also, the convergence granularity of the above method is excessive, it is easy to cover
Send out the provisional action more sensitive to the time such as capacity problem, such as large scale business activity of property wink.
Summary of the invention
The embodiment of the present invention provides a kind of cell capacity optimization method, device, equipment and computer storage medium, can
According to network public-opinion data predict cell load will be in congestion state Target cell, thus in time to Target cell into
The optimization of row capacity.
On the one hand, the embodiment of the present invention provides a kind of cell capacity optimization method, comprising:
Multiple groups relevant to the cell load of multiple cells in region to be optimized in a plurality of network public-opinion data are obtained to close
Key data；
Predict that cell load will be in congestion shape in multiple cells according to multiple groups critical data and a plurality of network public-opinion data
The Target cell of state；
The cell categories according to belonging to Target cell carry out capacity optimization to Target cell.
Preferably, critical data includes at least when and where relevant to event involved in network public-opinion data.
Further, it obtains relevant to the load of multiple cells in region to be optimized in a plurality of network public-opinion data
Multiple groups critical data includes:
Determine the corresponding part of speech of multiple words in each network public-opinion data；
Word relevant to cell load is obtained as critical data according to part of speech.
Further, predict that cell load will in multiple cells according to multiple groups critical data and a plurality of network public-opinion data
Target cell in congestion state includes:
Obtain network public-opinion data relevant to the object time and its corresponding critical data；
The corresponding feature vector of critical data is determined according to network public-opinion data, and based on hierarchical clustering method according to feature
Vector clusters critical data；
Predict that cell load corresponding with the object time will be in the Target cell of congestion state according to cluster result.
Preferably, the corresponding feature vector of critical data is determined according to network public-opinion data, and be based on hierarchical clustering method root
Critical data is clustered according to feature vector, comprising:
The ratio of the class number of clusters amount class number of clusters amount initial with feature vector after determining critical data cluster reaches predetermined
When threshold value, stopping clusters critical data.
Further, predict that cell load corresponding with the object time will be in the mesh of congestion state according to cluster result
Mark cell, comprising:
Predict that the target location of crowd massing will occur for the object time according to cluster result；
Determine that cell load will be in the Target cell of congestion state according to target location.
Further, the cell categories according to belonging to Target cell, carrying out capacity optimization to Target cell includes:
If Target cell is parcel cell, carrier wave shunting is carried out to Target cell；
If Target cell is middle Bao little Qu or big Bao little Qu, carrier wave is increased to Target cell.
Another aspect, the embodiment of the invention provides a kind of cell capacities to optimize device, and device includes:
Data extraction module is configured to obtain in a plurality of network public-opinion data and multiple cells in region to be optimized
The relevant multiple groups critical data of cell load；
Data processing module is configured to predict multiple cells according to multiple groups critical data and a plurality of network public-opinion data
Middle cell load will be in the Target cell of congestion state；
Optimizing cells module is configured to the cell categories according to belonging to Target cell, and it is excellent to carry out capacity to Target cell
Change.
In another aspect, the embodiment of the invention provides a kind of cell capacities to optimize equipment, the equipment includes: processor
And it is stored with the memory of computer program instructions；
Processor realizes above-mentioned cell capacity optimization method when executing computer program instructions.
In another aspect, being stored in computer storage medium the embodiment of the invention provides a kind of computer storage medium
Computer program instructions realize above-mentioned cell capacity optimization method when computer program instructions are executed by processor.
Cell capacity optimization method, device, equipment and the computer storage medium of the embodiment of the present invention can utilize net
Critical data relevant to the cell load of multiple cells in region to be optimized in network public sentiment data, and according to critical data
The Target cell that the cell load in region to be optimized will be in congestion state is predicted with network public-opinion data, thus according to
Do not have to cell categories belonging to Target cell, capacity optimization targetedly is carried out to Target cell, that can determine in time
Target cell to be optimized out, and prediction Target cell is improved using the reference data (network public-opinion data) of various dimensions
Accuracy, so as to which the capacity for carrying out diversified forms to Target cell optimizes, to realize diversified capacity optimization side
Case saves capacity and optimizes cost.
Compared to traditional dilatation way, the present invention, can be before cell capacity reaches bottleneck with more perspective, root
It is predicted that result targetedly optimized in advance, following userbase can be effectively coped with and increased, ensure user's sense
Know and network even running.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to required in the embodiment of the present invention
The attached drawing used is briefly described, for those of ordinary skill in the art, in the premise not made the creative labor
Under, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow diagram of cell capacity optimization method provided by one embodiment of the present invention；
Fig. 2 is the flow diagram provided by one embodiment of the present invention for obtaining network public-opinion data method；
Fig. 3 is an exemplary schematic diagram of the network public-opinion data in the embodiment of the present invention；
Fig. 4 is the flow diagram of the specific method of the step S110 in the embodiment of the present invention；
Fig. 5 is the flow diagram of the specific method of the step S120 in the embodiment of the present invention；
Fig. 6 is the schematic diagram of the cluster result obtained using the clustering method of the embodiment of the present invention；
Fig. 7 is the flow diagram of the specific method of the step S123 in the embodiment of the present invention.
Fig. 8 is that cluster result shown in Fig. 6 increases the schematic diagram after latitude and longitude information；
Fig. 9 is the structural schematic diagram of cell capacity optimization device provided by one embodiment of the present invention；
Figure 10 is the hardware structural diagram of cell capacity optimization provided in an embodiment of the present invention.
Specific embodiment
The feature and exemplary embodiment of various aspects of the invention is described more fully below, in order to make mesh of the invention
, technical solution and advantage be more clearly understood, below in conjunction with drawings and the specific embodiments, the present invention is carried out further detailed
Thin description.It should be understood that specific embodiment described herein is only configured to explain the present invention, it is not configured as limiting this
Invention.To those skilled in the art, the present invention can be the case where not needing some details in these details
Lower implementation.It is better to the present invention just for the sake of being provided by showing example of the invention to the description of embodiment below
Understand.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, without necessarily requiring or implying between these entities or operation
There are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant are intended to
Cover non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of person's equipment.In the absence of more restrictions, the element limited by sentence " including ... ", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
In order to solve prior art problem, the embodiment of the invention provides a kind of cell capacity optimization method, device, set
Standby and computer storage medium.Cell capacity optimization method is provided for the embodiments of the invention first below to be introduced.
Fig. 1 shows the flow diagram of cell capacity optimization method provided by one embodiment of the present invention.Such as Fig. 1 institute
Show, cell capacity optimization method includes:
It is relevant to the cell load of multiple cells in region to be optimized in S110, a plurality of network public-opinion data of acquisition
Multiple groups critical data；
S120, predict that cell load will be in multiple cells according to multiple groups critical data and a plurality of network public-opinion data
The Target cell of congestion state；
S130, the cell categories according to belonging to Target cell carry out capacity optimization to Target cell.
The cell capacity optimization method of the embodiment of the present invention, can be using in network public-opinion data and in region to be optimized
Multiple cells the relevant critical data of cell load, and predicted according to critical data and network public-opinion data to be optimized
Cell load in region will be in the Target cell of congestion state, thus do not have to cell categories according to belonging to Target cell,
Capacity optimization targetedly is carried out to Target cell, can determine Target cell to be optimized in time, and is utilized
The reference datas (network public-opinion data) of various dimensions improves the accuracy of prediction Target cell, so as to Target cell into
The capacity of row diversified forms optimizes, to realize diversified capacity prioritization scheme, saves capacity and optimizes cost.
In embodiments of the present invention, before step S110, it is also necessary to be obtained and region to be optimized based on internet data
Corresponding a plurality of network public-opinion data.
Due to network public-opinion data acquisition primarily directed to internet data information excavating, dug using data
Pick technology finds potential, valuable network public-opinion data in internet data, and it is to be optimized to be that the embodiment of the present invention is analyzed
The information source of Target cell.Under normal circumstances, the Web page that can be interacted with network data base includes a large amount of mutual
Networking data can be regarded as a huge network public sentiment information database.But due to the internet data in Web page
It is semi-structured or non-structured data, meanwhile, the interconnection netting index with the rapid growth of Web page, in Web page
According to being continuously updated, Web page is made to become the extremely strong information source of dynamic, causes to carry out network carriage using Web page
The acquisition of feelings data is complex.
Fig. 2 shows the flow diagrams provided by one embodiment of the present invention for obtaining network public-opinion data method.Such as figure
Shown in 2, obtaining network public-opinion data method may include:
S210, Web page relevant to region to be optimized is obtained in internet data by search engine；
S220, public feelings information is crawled from Web page using new Web Crawler；
S230, data parsing is carried out to public feelings information, obtains network public-opinion data, and respectively in the form of text data
Store each network public-opinion data.
In step S210, it can be scanned in a search engine using region to be optimized as descriptor.For example, to
When optimization region is Foochow, " Foochow " can be used as descriptor, be scanned in the search engines such as Baidu, 360, search dog,
To obtain Web page relevant to " Foochow ".
In step S220, microblogging, forum, discussion bar, news matchmaker that new Web Crawler includes from Web page can use
Corresponding public feelings information is obtained in the Webpages such as body, thus obtain various dimensions for predicting Target cell to be optimized
Reference data.
In step S230, since the public feelings information obtained in step S220 is generally character string, not can be used directly in
Therefore data analysis can carry out data parsing to public feelings information, will be converted into text with the public feelings information of string representation
Notebook data is as network public-opinion data.
The microblogging activity of registering is a kind of subjective behavior of people, since it has when and where information, thus can be preferably
The case where reflecting crowd massing occurred or imminent.In the following, to obtain public feelings information from microblogging loose-leaf of registering
For, the acquisition methods of the network public-opinion data of the embodiment of the present invention are illustrated:
Firstly, formulating data collection strategy based on region to be optimized, i.e., involved in the setting internet data of being acquired
Geographic coverage, and retrieved.
Then, it is chosen at microblogging and registers data of registering that place in activity is located in the regional scope as public feelings information.
Finally, due to Sina weibo api interface place/nearby_timeline is called to carry out data acquisition, acquisition
Public feelings information is the microblog data of json format, and therefore, it is necessary to the character strings of the microblog data to json format to parse,
To extract the body matter of microblog data, and it is stored as a plurality of network public-opinion number as shown in Figure 3 in a text form
According to.
Preferably, critical data described in the embodiment of the present invention includes at least and thing involved in network public-opinion data
The relevant when and where of part.Specifically, it can determine that may cause crowd involved in network public-opinion data gathers according to the time
The time that the event of collection occurs, it can determine that this may cause the locale of crowd massing according to place, for example,
Location name, address, place classification etc..Since the event may cause crowd massing, accordingly, it is possible to influence in region to be optimized
Multiple cells in cell relevant to the event cell load.Thus, it is possible to by involved in network public-opinion data
The relevant when and where of event is as critical data relevant to the cell load of multiple cells in region to be optimized.
It should be noted that in order to predict whether event will lead to involved in it better by network public-opinion data
The cell load of relevant cell is in congestion state, can also be by the relevant crowd of event involved in network public-opinion data
Scale is as critical data described in of the invention implement.
Fig. 4 shows the flow diagram of the specific method of the step S110 in the embodiment of the present invention.As shown in figure 4, step
Rapid S110, multiple groups key number relevant to the load of multiple cells in region to be optimized in a plurality of network public-opinion data is obtained
According to specific method include:
S111, the corresponding part of speech of multiple words in each network public-opinion data is determined；
S112, word relevant to cell load is obtained as critical data according to part of speech.
Since the network public-opinion data compared with the structural data in traditional database, obtained from Web page are
Semi-structured or non-structured data are difficult to directly obtain the pass to carry out data analysis from network public-opinion data
Key data, therefore, it is necessary to by a series of pretreatment, so as to grab out textual form from network public-opinion data
Critical data facilitates later use network public-opinion data and its critical data to analyze Target cell.
In step S111, it is necessary first to carry out word segmentation processing to network public-opinion data.Due in the embodiment of the present invention
In, network public-opinion data are stored with form of textual data, it is therefore possible to use Chinese lexical analysis device (Institute of
Computing Technology, Chinese Lexical Analysis System, ICTCLAS), to each network public-opinion
Data carry out text participle and obtain multiple words, carry out part-of-speech tagging to word, while identifying do not have in user-oriented dictionary
Neologisms, and the neologisms that will identify that are stored in user-oriented dictionary.
By taking critical data includes when and where relevant to event involved in network public-opinion data as an example, to step
S112 is described in detail.
After carrying out text participle and part-of-speech tagging to network public-opinion data, will first it can judge about involved
The year, month, day, hour, min Equal-time Data of time of event be included into chronological classification, and retain as critical data.By the tone
The excessively high or too low word of the frequency of occurrences in network public-opinion data such as word is filtered using " deactivated dictionary ", thus will
The stronger noun of event description, verb are screened as the data characteristics of network public-opinion data, divided according to the time
Class stores the data characteristics of each network public-opinion data, to reduce the dimension of the data characteristics of network public-opinion data.
Then feature extracting method is utilized, the network public-opinion number is obtained from the data characteristics of each network public-opinion data
According to the relevant place of related event.Wherein, feature extraction is to extract effectively and close in a kind of text data from after participle
The method of key information, the purpose is to the dimension of useful information and reduction data is isolated from noise data.Due to microblogging
Often there is certain isomery in the geography information that data include, i.e., exist sometimes for same geographical location a variety of different
Naming method, for example, the title of the geographical entity in place, be commonly called as and also known as etc..So in the side by feature extraction
It when formula obtains the related relevant place of event as critical data, needs to carry out purposive screening, for example, can incite somebody to action
The title of the geographical entity in place, be commonly called as and also known as etc. exclusive lists screened as keyword, with filter out about
The keyword in place is as critical data.Network public-opinion data shown in Fig. 3 are carried out with the sieve of the critical data about place
It is selected as example, the event content that network public-opinion data shown in Fig. 3 are related to is " on 2 11st, 2018 will be in the Da Minglukai of Foochow
Open up the gourmet festival ", therefore, can be analyzed according to this event content about the keyword in place and be [' Foochow ', ' cuisines ', '
Gourmet festival ', ' opens street ', ' cuisine variety street ', ' up to bright ', ' Da Minglu '], using these about place keyword as about place
Critical data, the selection result of the critical data about place can be made more accurate.
It should be noted that due in embodiments of the present invention, be cell load is likely to be at congestion state to
The Target cell of optimization is predicted, therefore, when network public-opinion data are carried out with the acquisition of critical data, only for data
It acquires network public-opinion data corresponding with event imminent after the time of analysis to be analyzed, to reduce data processing
Amount saves data processing cost, improves data-handling efficiency.
In embodiments of the present invention, the multiple groups network public-opinion data of each network public-opinion data acquisition will can be directed to
Data characteristics and its corresponding critical data are stored after temporally being classified, so as to it is subsequent extract with can be convenient to
The data characteristics and its corresponding critical data of the network public-opinion data of analysis.
Fig. 5 shows the flow diagram of the specific method of the step S120 in the embodiment of the present invention.As shown in figure 5, step
Rapid S120, predict that cell load will be in congestion shape in multiple cells according to multiple groups critical data and a plurality of network public-opinion data
The specific method of the Target cell of state includes:
S121, acquisition network public-opinion data relevant to the object time and its corresponding critical data；
S122, determine the corresponding feature vector of critical data according to network public-opinion data, and based on hierarchical clustering method according to
Feature vector clusters critical data；
S123, predict that cell load corresponding with the object time is small by the target in congestion state according to cluster result
Area.
Wherein, as based on network public-opinion data using network public-opinion data and its corresponding critical data carry out to
The step S120 of the forecast analysis of the Target cell of optimization, main purpose are to utilization step S110 to network public-opinion data
In the data characteristics and its corresponding critical data of the network public-opinion data obtained after being handled about place keyword into
Row analysis and excavation, to find focus incident in the event involved in network public-opinion data and carry out chasing after for focus incident
Track, finally to determine Target cell.In the following, to based on network public-opinion data using the data characteristics of network public-opinion data and
Keyword in its corresponding critical data about place carries out the specific method of the forecast analysis of Target cell to be optimized
It is described in detail.
When having obtained network public-opinion data relevant to the object time and its corresponding critical data using step S121
Afterwards, that is, enter the forecast analysis process of Target cell to be optimized.Wherein, the object time, which can according to need, is configured, example
Such as, certain time etc. in certain section of date, some date or some date.
Firstly, determining that the keyword about place exists using vector space model (Vector Space Model, VSM)
The corresponding feature vector of the data characteristics of network public-opinion data.VSM be late 1960s by the propositions such as Salton to
The model for indicating the importance of a certain word in text data, is the main model in current natural language processing, uses vector
Spatial model indicates text data, and carries out feature selecting and weight calculation to the word in text data, forms a N-dimensional
Space vector.
Wherein, word frequency and inverse document frequency (Term Frequency-inverse Document Frequency, TF-
IDF) statistical method is a kind of classical weighing computation method based on VSM model being put forward for the first time by Jones, is applied earliest
In information retrieval field, to assess a words for the weight of a document or a classification in file set or corpus
Want degree.The main thought of TF-IDF statistical method is: if the frequency that occurs in a classification of some word or word compared with
Height, and seldom occur in other classifications, then it is assumed that this word or word have good class discrimination ability, are adapted to
Classification.In embodiments of the present invention, TF-IDF statistical method can be used, to the keyword about place for a plurality of network
The importance of public sentiment data is calculated, to determine the keyword in critical data about place for a plurality of network public-opinion number
According to significance level, determine whether to carry out subsequent analysis processing with it.
Specifically, the calculation method of TF-IDF statistical method is as follows:
Firstly, determining word frequency TF (i, j), word frequency TF (i, j) indicates time that keyword i occurs in network public-opinion data j
Number.
Then, it is determined that inverse text frequency IDF, the calculation formula of inverse text frequency IDF are as follows:
IDF=log (N/Ni+0.01)
Wherein, N indicates that the sum of network public-opinion data, Ni indicate the quantity of the network public-opinion data with keyword i.
Finally, using the product of word frequency TF (i, j) and inverse text frequency IDF as the characteristic vector W [j] of keyword i
[i], this feature vector W [j] [i] are a two-dimensional matrix, the calculation formula of characteristic vector W [j] [i] are as follows:
W [j] [i]=TF (i, j) * IDF (i)
By the characteristic vector W [j] [i] for counting keyword i, it can it is micro- simply, intuitively, fast to obtain each
The weight of each keyword i in rich data.The feature vector of the keyword of all-network public sentiment data is formed into matrix, i.e.,
It can get vector space model.
After obtaining vector space model and the weight of each keyword has been determined, hierarchical clustering method root can be based on
Critical data is clustered according to feature vector.Specific address can will press spy about the keyword in place in critical data
It levies vector and carries out descending arrangement, and set a weight threshold, filtered out in critical data according to the weight threshold for carrying out
The keyword about place of cluster.
In embodiments of the present invention, by filtering out the keyword about place in critical data for being clustered
It determines focus incident, finds that algorithm, hot spot find that algorithm is essentially belong in data mining using hot spot
Text Clustering Algorithm, concrete implementation process are as follows: the pass about place for being used to cluster in critical data will be filtered out
Keyword is clustered, to find focus incident from network public-opinion data.With the traditional vector space based on TF-IDF of utilization
Model directly carries out cluster and compares, and the embodiment of the present invention avoids because not accounting for the similar feelings of existing concept between word
Condition, and the problem of influence the accuracy of data clusters, it particular avoids when Chinese text is clustered, what is obtained is similar
Degree deviates larger problem with actual conditions.
It in embodiments of the present invention, can be using a kind of hierarchical clustering method from bottom to top to filtering out in critical data
The keyword about place for being clustered is clustered, and this method is a kind of unsupervised learning method, core ideas
Merging between class cluster and class cluster, during cluster, all keywords start when respectively at a class cluster, later
Constantly repeat to merge two apart from nearest class cluster, until class number of clusters amount reaches specified quantity.
Further, in embodiments of the present invention, it is using the key point that hierarchical clustering method is clustered two clear
The distance between class cluster (measuring similarity), the calculation method of common measuring similarity have following three kinds:
1, single-stranded method: the similarity by the distance between two nearest points of different two class clusters as two class clusters.
2, full chain method: the similarity by the distance between two farthest points of different two class clusters as two class clusters.
3, group average method: all the points combination from two inhomogeneity clusters is fetched, distance between points is calculated, with it
Similarity of the average value as two class clusters.
Specifically, in embodiments of the present invention, the tool keyword about place clustered using hierarchical clustering method
Body method includes the following steps:
A) using the keyword about place in each network public-opinion data as a class cluster, n class cluster mesh is constructed
Network public-opinion data set D={ d1 ..., di ..., dn }, the class cluster Ci={ di } of single network public sentiment data in topic are marked,
These class clusters constitute network public-opinion data set D a cluster C=C1 ..., Ci ..., Cn }.
B) the similitude sim (Ci, Cj) between class cluster (Ci, Cj) two-by-two is calculated in cluster C, similarity matrix S is denoted as；
C) the maximum two class clusters max of similarity (sim (Ci, Cj)) is chosen, and Ci and Cj is merged into a new class
Cluster C=Ci ∪ Cj, thus a new class cluster C={ C1 ..., Cn- 1 } for constituting D, while updating similarity matrix S；
D) it is equal to 1 if class number of clusters amount or terminates if reaching specified quantity, otherwise repeatedly step b, c.
Since when class number of clusters amount is equal to 1, the keyword in all about place will be clustered into a class cluster, cause to gather
Class is excessive, so that focus incident can not be obtained.Therefore, in embodiments of the present invention, step S122, according to network public-opinion data
It determines the corresponding feature vector of critical data, and critical data is clustered according to feature vector based on hierarchical clustering method, wrap
Include: the ratio of class number of clusters amount and the initial class number of clusters amount of feature vector after determining critical data cluster reaches predetermined threshold
When, stopping clusters critical data.
Specifically, the ratio of class number of clusters amount after cluster and the initial class number of clusters amount of feature vector reaches predetermined threshold
When, it can determine that class number of clusters amount reaches specified quantity, therefore, the cluster to keyword can be terminated.
In an example of the present invention, can extract in a plurality of network public-opinion data in the object time about place
Keyword then clustered using hierarchical clustering algorithm, occur excessive class cluster in order to prevent and show with what class cluster merged
As providing that the ratio of the class number of clusters amount initial with feature vector of class number of clusters amount after cluster reaches when clustering algorithm executes
10% is used as exit criteria, to guarantee that clustering procedure obtains suitable cluster result.At this point, obtained cluster result such as Fig. 6 institute
Show, according in the cluster result about place keyword frequency of occurrence, can both predict mesh relevant to the keyword
Mark cell.
Fig. 7 shows the flow diagram of the specific method of the step S123 in the embodiment of the present invention.As shown in fig. 7, step
Rapid S123, predict that cell load corresponding with the object time will be in the Target cell of congestion state, packet according to cluster result
It includes:
S310, predict that the target location of crowd massing will occur for the object time according to cluster result；
S320, determine that cell load will be in the Target cell of congestion state according to target location.
Illustrate step S310 by taking cluster result shown in fig. 6 as an example.It can be arranged according to the frequency that each place occurs
Sequence is likely to occur the target location of crowd massing using the more place of frequency of occurrence as the object time.It specifically, can be with
It selects the place of the forward preset quantity of the frequency as target location, also can choose the place that the frequency is greater than the predetermined frequency
As target location.
After target location has been determined, both the geographical location of available target location, the i.e. longitude and latitude of target location were believed
Breath.But the data disclosed in network public-opinion data about place generally relate only to the location name and address letter in the place
Breath, will not provide specific latitude and longitude information.For not reporting the place of latitude and longitude information, can be picked up by Baidu's coordinate
System is taken, generates the request of target location coordinate resolution, according to syntax rule to find formatting from internet data
The latitude and longitude information of the target location.Finally, the latitude and longitude information can be saved in cluster result, as shown in Figure 8.
It, both can be according to the geographical location of the target location by its week after the latitude and longitude information of target location has been determined
It encloses the cell in preset range and is set as Target cell, the quantity of Target cell can be for one or multiple.For example,
It is Target cell that the cell in the region in 500 meters of target location radius, which can be set,.
In embodiments of the present invention, step S130, cell categories according to belonging to Target cell carry out Target cell
Capacity optimizes
If Target cell is parcel cell, carrier wave shunting is carried out to Target cell；
If Target cell is middle Bao little Qu or big Bao little Qu, carrier wave is increased to Target cell.
Wherein, the scale of crowd massing can be pressed according to frequency of occurrence of the target location in cluster result first big
It is medium and small to classify, it is then based on the scale of crowd massing and the current setting parameter of Target cell, Target cell is divided into small
The cell categories such as packet cell, middle Bao little Qu or big packet cell.Then, for the cell categories belonging to it, it is taken different
Capacity prioritization scheme.
When Target cell is parcel cell, only by modifying the cell parameter of the cell, by the carrier wave of the Target cell
The carrier wave of the similar frequency bands of periphery idle district is branched to, or the carrier wave of the Target cell is branched into the Target cell
The carrier wave of other idle frequency ranges, to realize the carrier equalisation of Target cell and peripheral cell, thus without increasing hardware device
Under the premise of, it realizes and the capacity of Target cell is optimized, save capacity and optimize cost.When Target cell be middle packet cell or
When big packet cell, the number of carrier wave of Target cell can be increased, to realize cell capacity by the method for increase hardware device
Optimization.
It can be seen that the cell capacity optimization method of the embodiment of the present invention, it can be based on big data to Internet user's
The target location that may assemble is predicted, indirectly to predict Target cell to be optimized, improves cell capacity-enlarging scheme
Accuracy, change the single disadvantage of reference frame dimension.
Fig. 9 shows the structural schematic diagram of cell capacity optimization device provided by one embodiment of the present invention.Such as Fig. 9 institute
It states, cell capacity optimization device includes:
Data extraction module 401, be configured to obtain in a plurality of network public-opinion data with it is multiple small in region to be optimized
The relevant multiple groups critical data of the cell load in area；
Data processing module 402 is configured to multiple small according to multiple groups critical data and the prediction of a plurality of network public-opinion data
Cell load will be in the Target cell of congestion state in area；
Optimizing cells module 403 is configured to the cell categories according to belonging to Target cell, holds to Target cell
Amount optimization.
Wherein, critical data includes at least when and where relevant to event involved in network public-opinion data.
In embodiments of the present invention, cell capacity optimization device further includes data acquisition module 404, is configured to
Internet data obtains a plurality of network public-opinion data corresponding with region to be optimized.
In embodiments of the present invention, data extraction module 401 is further configured to: determining each network public-opinion data
In the corresponding part of speech of multiple words；Word relevant to cell load is obtained as critical data according to part of speech.
In embodiments of the present invention, data processing module 402 is further configured to: being obtained relevant to the object time
Network public-opinion data and its corresponding critical data；The corresponding feature vector of critical data is determined according to network public-opinion data, and
Critical data is clustered according to feature vector based on hierarchical clustering method；It is predicted according to cluster result corresponding with the object time
Cell load will be in congestion state Target cell.
Further, the corresponding feature vector of critical data is determined according to network public-opinion data, and be based on hierarchical clustering method
Critical data is clustered according to feature vector, comprising: class number of clusters amount and feature vector after determining critical data cluster
When the ratio of initial class number of clusters amount reaches predetermined threshold, stopping clusters critical data.
Further, predict that cell load corresponding with the object time will be in the mesh of congestion state according to cluster result
Mark cell, comprising: predict that the target location of crowd massing will occur for the object time according to cluster result；It is true according to target location
Determine the Target cell that cell load will be in congestion state.
In embodiments of the present invention, optimizing cells module 403 is further configured to: if Target cell is parcel cell,
Carrier wave shunting is carried out to Target cell；If Target cell is middle Bao little Qu or big Bao little Qu, carrier wave is increased to Target cell.
The cell capacity of the embodiment of the present invention optimizes device, can be realized based on network public-opinion data to cell capacity
Automatic Optimal, specifically, can predict that the network user may assemble by acquisition to network public-opinion data and processing when
Between, place, and the scale of crowd massing can also be predicted, so that it is determined that then target location out passes through target location
Latitude and longitude information searches out Target cell to be optimized, carries out cell capacity optimization to Target cell.
In conclusion the cell capacity optimization method and device of the embodiment of the present invention, can be based on time and geographical location
The target position for being likely to occur crowd massing is judged in advance, and determines Target cell to be optimized, is the appearance of cell
Amount optimization provides more decision-making foundations.Compared to traditional dilatation way, the present invention is with more perspective, in cell capacity
Targetedly optimized in advance before reaching bottleneck according to the result of prediction, following userbase can be effectively coped with and increased
It is long, ensure user's perception and network even running.
Figure 10 shows the hardware structural diagram of cell capacity optimization provided in an embodiment of the present invention.
Cell capacity optimization may include processor 501 and the memory 502 for being stored with computer program instructions.
Specifically, above-mentioned processor 501 may include central processing unit (CPU) or specific integrated circuit
(Application Specific Integrated Circuit, ASIC), or may be configured to implement of the invention real
Apply one or more integrated circuits of example.
Memory 502 may include the mass storage for data or instruction.For example it rather than limits, storage
Device 502 may include hard disk drive (Hard Disk Drive, HDD), floppy disk drive, flash memory, CD, magneto-optic disk, tape
Or the group of universal serial bus (Universal Serial Bus, USB) driver or two or more the above
It closes.In a suitable case, memory 502 may include the medium of removable or non-removable (or fixed).In suitable situation
Under, memory 502 can be inside or outside synthesized gateway disaster tolerance equipment.In a particular embodiment, memory 502 is non-easy
The property lost solid-state memory.In a particular embodiment, memory 502 includes read-only memory (ROM).In a suitable case, should
ROM can be the ROM of masked edit program, programming ROM (PROM), erasable PROM (EPROM), electric erasable PROM
(EEPROM), electrically-alterable ROM (EAROM) or the combination of flash memory or two or more the above.
Processor 501 is by reading and executing the computer program instructions stored in memory 502, to realize above-mentioned reality
Apply any one cell capacity optimization method in example.
In one example, cell capacity optimization equipment can also respectively include communication interface 503 and bus 510.Wherein,
As shown in Figure 10, processor 501, memory 502, communication interface 503 connect by bus 510 and complete mutual communication.
Communication interface 503 is mainly used for realizing in the embodiment of the present invention between each module, device, unit and/or equipment
Communication.
Bus 510 includes hardware, software or both, and the component of online data charge on traffic equipment is coupled to each other one
It rises.For example it rather than limits, bus may include accelerated graphics port (AGP) or other graphics bus, enhancing industrial standard frame
Structure (EISA) bus, front side bus (FSB), super transmission (HT) interconnection, Industry Standard Architecture (ISA) bus, infinite bandwidth are mutual
Company, low pin count (LPC) bus, memory bus, micro- channel architecture (MCA) bus, peripheral component interconnection (PCI) bus,
PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association part (VLB)
The combination of bus or other suitable buses or two or more the above.In a suitable case, bus 510 can
Including one or more buses.Although specific bus has been described and illustrated in the embodiment of the present invention, the present invention considers any conjunction
Suitable bus or interconnection.
Cell capacity optimization equipment can execute the cell capacity optimization method in the embodiment of the present invention, to realize
In conjunction with the cell capacity optimization method and device of the application.
In addition, in conjunction with the cell capacity optimization method in above-described embodiment, the embodiment of the present invention can provide a kind of computer
Storage medium is realized.Computer program instructions are stored in the computer storage medium；The computer program instructions are processed
Device realizes any one cell capacity optimization method in above-described embodiment when executing.
It should be clear that the invention is not limited to specific configuration described above and shown in figure and processing.
For brevity, it is omitted here the detailed description to known method.In the above-described embodiments, it has been described and illustrated several
Specific step is as example.But method process of the invention is not limited to described and illustrated specific steps, ability
The technical staff in domain can be variously modified, modification and addition, or change the step it after understanding spirit of the invention
Between sequence.
Functional block shown in structures described above block diagram can be implemented as hardware, software, firmware or their group
It closes.When realizing in hardware, it may, for example, be electronic circuit, specific integrated circuit (ASIC), firmware appropriate, insert
Part, function card etc..When being realized with software mode, element of the invention be used to execute the program of required task or
Code segment.Perhaps code segment can store in machine readable media program or the data-signal by carrying in carrier wave exists
Transmission medium or communication links are sent." machine readable media " may include any Jie for capableing of storage or transmission information
Matter.The example of machine readable media include electronic circuit, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM),
Floppy disk, CD-ROM, CD, hard disk, fiber medium, radio frequency (RF) link, etc..Code segment can be via such as internet, interior
The computer network of networking etc. is downloaded.
It should also be noted that, the exemplary embodiment referred in the present invention, is retouched based on a series of step or device
State certain methods or system.But the present invention is not limited to the sequence of above-mentioned steps, that is to say, that can be according in embodiment
The sequence referred to executes step, may also be distinct from that the sequence in embodiment or several steps are performed simultaneously.
The above description is merely a specific embodiment, and those skilled in the art can be understood that
It arrives, for convenience of description and succinctly, system, the specific work process of module and unit of foregoing description can refer to aforementioned
Corresponding process in embodiment of the method, details are not described herein.It should be understood that scope of protection of the present invention is not limited thereto, it is any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or
Replacement, these modifications or substitutions should be covered by the protection scope of the present invention.
Claims (10)
1. a kind of cell capacity optimization method characterized by comprising
Obtain multiple groups key number relevant to the cell load of multiple cells in region to be optimized in a plurality of network public-opinion data
According to；
Cell load described in the multiple cell is predicted according to the multiple groups critical data and a plurality of network public-opinion data
The Target cell of congestion state will be in；
According to cell categories belonging to the Target cell, capacity optimization is carried out to the Target cell.
2. cell capacity optimization method according to claim 1, which is characterized in that the critical data includes at least and institute
State the relevant when and where of event involved in network public-opinion data.
3. cell capacity optimization method according to claim 1, which is characterized in that obtain in a plurality of network public-opinion data with
The relevant multiple groups critical data of the load of multiple cells in region to be optimized includes:
Determine the corresponding part of speech of multiple words in network public-opinion data described in each item；
The word relevant to the cell load is obtained as the critical data according to the part of speech.
4. cell capacity optimization method according to claim 1, which is characterized in that according to the multiple groups critical data and institute
It states a plurality of network public-opinion data and predicts that the Target cell in congestion state is included: by cell load described in the multiple cell
Obtain the network public-opinion data relevant to the object time and its corresponding critical data；
The corresponding feature vector of the critical data is determined according to the network public-opinion data, and based on hierarchical clustering method according to institute
Feature vector is stated to cluster the critical data；
Predict that the cell load corresponding with the object time will be in the target of congestion state according to cluster result
Cell.
5. cell capacity optimization method according to claim 4, which is characterized in that determined according to the network public-opinion data
The corresponding feature vector of the critical data, and the critical data is carried out according to described eigenvector based on hierarchical clustering method
Cluster, comprising:
The ratio of the class number of clusters amount class number of clusters amount initial with described eigenvector after determining critical data cluster reaches
When predetermined threshold, stopping clusters the critical data.
6. cell capacity optimization method according to claim 4, which is characterized in that according to cluster result prediction and the mesh
Mark the Target cell that the time corresponding cell load will be in congestion state, comprising:
Predict that the target location of crowd massing will occur for the object time according to the cluster result；
Determine that the cell load will be in the Target cell of congestion state according to the target location.
7. cell capacity optimization method according to claim 1, which is characterized in that small according to belonging to the Target cell
Area's classification, carrying out capacity optimization to the Target cell includes:
If the Target cell is parcel cell, carrier wave shunting is carried out to the Target cell；
If the Target cell is middle Bao little Qu or big Bao little Qu, carrier wave is increased to the Target cell.
8. a kind of cell capacity optimizes device, which is characterized in that described device includes:
Data extraction module is configured to obtain the cell in a plurality of network public-opinion data with multiple cells in region to be optimized
Load relevant multiple groups critical data；
Data processing module is configured to described more according to the multiple groups critical data and a plurality of network public-opinion data prediction
Cell load described in a cell will be in the Target cell of congestion state；
Optimizing cells module is configured to the cell categories according to belonging to the Target cell, holds to the Target cell
Amount optimization.
9. a kind of cell capacity optimizes equipment, which is characterized in that the equipment includes: processor and is stored with computer program
The memory of instruction；
The processor realizes the cell capacity as described in claim 1-7 any one when executing the computer program instructions
Optimization method.
10. a kind of computer storage medium, which is characterized in that be stored with computer program in the computer storage medium and refer to
It enables, realizes that the cell capacity as described in claim 1-7 any one is excellent when the computer program instructions are executed by processor
Change method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811424903.7A CN109526027B (en) | 2018-11-27 | 2018-11-27 | Cell capacity optimization method, device, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811424903.7A CN109526027B (en) | 2018-11-27 | 2018-11-27 | Cell capacity optimization method, device, equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109526027A true CN109526027A (en) | 2019-03-26 |
| CN109526027B CN109526027B (en) | 2022-07-01 |
Family
ID=65794445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811424903.7A Active CN109526027B (en) | 2018-11-27 | 2018-11-27 | Cell capacity optimization method, device, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109526027B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110944339A (en) * | 2019-10-12 | 2020-03-31 | 中国通信建设集团设计院有限公司 | Load distribution method, device and equipment for cell in base station |
| CN112911611A (en) * | 2019-11-19 | 2021-06-04 | 中国移动通信集团山东有限公司 | Cell optimization method, device, storage medium and source base station |
| CN114173318A (en) * | 2021-12-09 | 2022-03-11 | 中国联合网络通信集团有限公司 | Method, device and equipment for identifying to-be-optimized area |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763431A (en) * | 2010-01-06 | 2010-06-30 | 电子科技大学 | PL clustering method based on massive network public sentiment information |
| CN103246644A (en) * | 2013-04-02 | 2013-08-14 | 亿赞普(北京)科技有限公司 | Method and device for processing Internet public opinion information |
| CN103324665A (en) * | 2013-05-14 | 2013-09-25 | 亿赞普(北京)科技有限公司 | Hot spot information extraction method and device based on micro-blog |
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| US20140181100A1 (en) * | 2005-09-14 | 2014-06-26 | Millennial Media, Inc. | Predictive Text Completion For A Mobile Communication Facility |
| CN104080091A (en) * | 2014-07-22 | 2014-10-01 | 重庆邮电大学 | Family base station frequency spectrum allocation method based on load prediction grouping in layered heterogenous network |
| CN104113857A (en) * | 2013-04-18 | 2014-10-22 | 中国移动通信集团甘肃有限公司 | Wireless capacity optimization method and device |
| CN104794161A (en) * | 2015-03-24 | 2015-07-22 | 浪潮集团有限公司 | Method for monitoring network public opinions |
| CN105068991A (en) * | 2015-07-30 | 2015-11-18 | 成都鼎智汇科技有限公司 | Big data based public sentiment discovery method |
| CN105208603A (en) * | 2015-10-15 | 2015-12-30 | 南京理工大学 | LTE network multi-target load balancing method |
| CN105472660A (en) * | 2014-09-11 | 2016-04-06 | 中国移动通信集团公司 | Load balancing method and system and network equipment |
| CN107330557A (en) * | 2017-06-28 | 2017-11-07 | 中国石油大学(华东) | It is a kind of to be divided based on community and the public sentiment hot tracking of entropy and Forecasting Methodology and device |
| US20170345105A1 (en) * | 2014-03-31 | 2017-11-30 | Monticello Enterprises, Llc | System and method for providing multiple payment method options to users in connection with a browser payment request api |
| CN108321810A (en) * | 2018-02-12 | 2018-07-24 | 华南理工大学 | Inhibit the distribution Multiple Time Scales powerless control method of grid-connected voltage fluctuation |
| CN108845881A (en) * | 2018-05-30 | 2018-11-20 | 有米科技股份有限公司 | The method and device of server capacity dynamic adjustment |
-
2018
- 2018-11-27 CN CN201811424903.7A patent/CN109526027B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140181100A1 (en) * | 2005-09-14 | 2014-06-26 | Millennial Media, Inc. | Predictive Text Completion For A Mobile Communication Facility |
| CN101763431A (en) * | 2010-01-06 | 2010-06-30 | 电子科技大学 | PL clustering method based on massive network public sentiment information |
| CN103246644A (en) * | 2013-04-02 | 2013-08-14 | 亿赞普(北京)科技有限公司 | Method and device for processing Internet public opinion information |
| CN104113857A (en) * | 2013-04-18 | 2014-10-22 | 中国移动通信集团甘肃有限公司 | Wireless capacity optimization method and device |
| CN103324665A (en) * | 2013-05-14 | 2013-09-25 | 亿赞普(北京)科技有限公司 | Hot spot information extraction method and device based on micro-blog |
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| US20170345105A1 (en) * | 2014-03-31 | 2017-11-30 | Monticello Enterprises, Llc | System and method for providing multiple payment method options to users in connection with a browser payment request api |
| CN104080091A (en) * | 2014-07-22 | 2014-10-01 | 重庆邮电大学 | Family base station frequency spectrum allocation method based on load prediction grouping in layered heterogenous network |
| CN105472660A (en) * | 2014-09-11 | 2016-04-06 | 中国移动通信集团公司 | Load balancing method and system and network equipment |
| CN104794161A (en) * | 2015-03-24 | 2015-07-22 | 浪潮集团有限公司 | Method for monitoring network public opinions |
| CN105068991A (en) * | 2015-07-30 | 2015-11-18 | 成都鼎智汇科技有限公司 | Big data based public sentiment discovery method |
| CN105208603A (en) * | 2015-10-15 | 2015-12-30 | 南京理工大学 | LTE network multi-target load balancing method |
| CN107330557A (en) * | 2017-06-28 | 2017-11-07 | 中国石油大学(华东) | It is a kind of to be divided based on community and the public sentiment hot tracking of entropy and Forecasting Methodology and device |
| CN108321810A (en) * | 2018-02-12 | 2018-07-24 | 华南理工大学 | Inhibit the distribution Multiple Time Scales powerless control method of grid-connected voltage fluctuation |
| CN108845881A (en) * | 2018-05-30 | 2018-11-20 | 有米科技股份有限公司 | The method and device of server capacity dynamic adjustment |
Non-Patent Citations (1)
| Title |
|---|
| 高欢: ""基于流式计算的网络舆情分析模型研究"", 《情报学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110944339A (en) * | 2019-10-12 | 2020-03-31 | 中国通信建设集团设计院有限公司 | Load distribution method, device and equipment for cell in base station |
| CN110944339B (en) * | 2019-10-12 | 2022-09-30 | 中国通信建设集团设计院有限公司 | Load distribution method, device and equipment for cell in base station |
| CN112911611A (en) * | 2019-11-19 | 2021-06-04 | 中国移动通信集团山东有限公司 | Cell optimization method, device, storage medium and source base station |
| CN114173318A (en) * | 2021-12-09 | 2022-03-11 | 中国联合网络通信集团有限公司 | Method, device and equipment for identifying to-be-optimized area |
| CN114173318B (en) * | 2021-12-09 | 2023-05-12 | 中国联合网络通信集团有限公司 | Method, device and equipment for identifying region to be optimized |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109526027B (en) | 2022-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8244224B2 (en) | Providing customized information to a user based on identifying a trend | |
| CN103176983B (en) | A kind of event method for early warning based on internet information | |
| CN107862022B (en) | Culture resource recommendation system | |
| CN102760138B (en) | Classification method and device for user network behaviors and search method and device for user network behaviors | |
| Cai et al. | What are popular: exploring twitter features for event detection, tracking and visualization | |
| CN106600960A (en) | Traffic travel origin and destination identification method based on space-time clustering analysis algorithm | |
| CN104281607A (en) | Microblog hot topic analyzing method | |
| CN109526027A (en) | A kind of cell capacity optimization method, device, equipment and computer storage medium | |
| CN101404033A (en) | Automatic generation method and system for noumenon hierarchical structure | |
| CN112738729B (en) | Method and system for discriminating visiting and returning tourists through mobile phone signaling data | |
| US20170169096A1 (en) | Methods and systems for analyzing reading logs and documents thereof | |
| CN103810162A (en) | Method and system for recommending network information | |
| CN110232126A (en) | Hot spot method for digging and server and computer readable storage medium | |
| CN111159243A (en) | User type identification method, device, equipment and storage medium | |
| CN111447575A (en) | Short message pushing method, device, equipment and storage medium | |
| CN114330329A (en) | Service content searching method and device, electronic equipment and storage medium | |
| CN103324641A (en) | Information record recommendation method and device | |
| CN113449077B (en) | News heat calculation method, device and storage medium | |
| KR101621735B1 (en) | Recommended search word providing method and system | |
| CN113282641A (en) | Webpage search data information intelligent classification management method and system based on user behavior deep analysis and computer storage medium | |
| CN107734534B (en) | Network load evaluation method and device | |
| Ma et al. | Advanced deep web crawler based on Dom | |
| CN111105117B (en) | User information determining method and device | |
| CN101980209B (en) | Adaptive multi-field search engine calling method and system | |
| CN114648010A (en) | Data table standardization method, device, equipment and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |